Results 151 to 160 of about 3,080,648 (304)

Long-tailed Adversarial Training with Self-Distillation

CoRR
ICLR 2025.
Seungju Cho, Hongsin Lee, Changick Kim
openaire   +3 more sources

Chitosan‐Carbon Dot Composite Materials Form a Leaf Surface Barrier to Mitigate the Enrichment and Invasion of Nanoplastics: From Leaf Interface to Systemic Response

Advanced Science, EarlyView.
Foliar spraying of CS‐CDs can form a film on the leaves of Brassica rapa, effectively reducing the enrichment and absorption of PS in the leaves, while increasing the biomass and nutrient content of the plants. In addition, CS‐CDs can also enrich the interfoliar microbial community and activate the plant's own defense metabolic pathways.
Beibei Zhao, Mei Li, Mengjiao Fan, Chuanhuan Liu, Jie Jiang, Jia Song, Yingzhu Liu   +6 more
wiley   +1 more source

Online Prototype Angular Balanced Self-Distillation for Non-Ideal Annotation in Remote Sensing Image Segmentation

Remote Sensing
This paper proposes an Online Prototype Angular Balanced Self-Distillation (OPAB) framework to address the challenges posed by non-ideal annotation in remote sensing image semantic segmentation.
Hailun Liang, Haowen Zheng, Jing Huang, Hui Ma, Yanyan Liang   +4 more
doaj   +1 more source

Noninvasive Focal Gene Delivery into the Cerebellum of Non‐Human Primates using Focused Ultrasound

Advanced Science, EarlyView.
Focal and non‐invasive viral vector delivery in non‐human primates remains a major challenge in translational neuroscience. Low‐intensity focused ultrasound was used to transiently open the blood–brain barrier and enable targeted gene delivery to the cerebellum.
Noelia Esteban‐García, José A. Pineda‐Pardo, Inés Trigo‐Damas, Marta Gutiérrez, Marta Castillo‐Ortiz, Megan Carrillo, Alejandro Reinares‐Sebastian, Víctor Medina‐Chavarrías, Itay Rachmilevitch, Masahiko Takada, José A. Obeso, Javier Blesa   +11 more
wiley   +1 more source

Self‐Powered Bearing Sensing and Real‐Time Fault Diagnosis Enabled by Non‐Invasive Triboelectric Sensors and Edge AI Acceleration

Advanced Science, EarlyView.
This study achieves the synergistic integration of self‐powered sensing and edge AI acceleration to establish a real‐time fault diagnosis system. The proposed TENG‐based self‐powered bearing sensor (NSE‐TBS) and FPGA‐accelerated edge AI framework fundamentally break through the inherent limitations of conventional monitoring systems, including complex ...
Kehui Zhu, Zhongheng Liu, Xinming Li, Jinrui Zhang, Meng Li, Yiming Guo, Lihua Han, Yanxue Wang   +7 more
wiley   +1 more source

Enhancing Arabic Multi-Task Sentiment Analysis Through Distillation and Adversarial Training

Machine Learning and Knowledge Extraction
The rapid growth of Arabic social media content requires the development of accurate and efficient methods for sentiment analysis. We propose a resource-efficient multi-task learning (MTL) framework for modern standard Arabic (MSA).
Hafida Hidani, Safâa El Ouahabi, Mouncef Filali Bouami   +2 more
doaj   +1 more source

Destilação por película para misturas binárias [PDF]

, 2013
Dissertação (mestrado) - Universidade Federal de Santa Catarina, Centro Tecnológico, Programa de Pós-Graduação em Engenharia Química, Florianópolis, 2013A operação de colunas de destilação é um processo dispendioso em vários sentidos.
Parisotto, Iaçanã George Berté
core  

Engineering Neuronal Network Connectivity Through Precise and Scalable Electrical Modulation

Advanced Science, EarlyView.
This study presents a scalable all‐electrical method for precise neuronal‐circuit reconfiguration based on high‐density microelectrode arrays. By employing biologically inspired plasticity rules, targeted connectivity changes were successfully induced and quantified across diverse neuronal preparations.
Sreedhar S. Kumar, Yannaël Bossard, Rachel Sava, Tobias Gänswein, Lorenca Sadiraj, Jean‐Samuel Dupré, Manuel Schröter, J. Gray Camp, Fernando Cardes, Julian Bartram, Andreas Hierlemann   +10 more
wiley   +1 more source

Slot Attention with Re-Initialization and Self-Distillation

Proceedings of the 33rd ACM International Conference on Multimedia
Unlike popular solutions based on dense feature maps, Object-Centric Learning (OCL) represents visual scenes as sub-symbolic object-level feature vectors, termed slots, which are highly versatile for tasks involving visual modalities. OCL typically aggregates object superpixels into slots by iteratively applying competitive cross attention, known as ...
Rongzhen Zhao, Yi Zhao 0014, Juho Kannala, Joni Pajarinen   +3 more
openaire   +3 more sources

WTAP‐Mediated m6A Modification Targets the LRP1‐Lipid Metabolism Axis to Regulate Joint Cartilage Regeneration

Advanced Science, EarlyView.
WTAP drives cartilage regeneration by activating an LRP1‐dependent lipid metabolic program in macrophages, enhancing IL‐10 and TGF‐β secretion to promote chondrogenic differentiation. Leveraging this mechanism, virtual screening identifies LRP1‐targeting compounds that effectively stimulate cartilage repair, highlighting a druggable epigenetic ...
Chenyan Huang, Chenyu Deng, Zhengrong Gao, Chen Chen, Huimin Zheng, Yue Yang, Yan Wei   +6 more
wiley   +1 more source